{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:05:34Z","timestamp":1777889134196,"version":"3.51.4"},"reference-count":69,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02080","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"22404-22414","source":"Crossref","is-referenced-by-count":0,"title":["GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices"],"prefix":"10.1109","author":[{"given":"Quanfeng","family":"Lu","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenqi","family":"Shao","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zitao","family":"Liu","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lingxiao","family":"Du","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fanqing","family":"Meng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Boxuan","family":"Li","sequence":"additional","affiliation":[{"name":"Nanjing University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Botong","family":"Chen","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology,Shenzhen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Siyuan","family":"Huang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kaipeng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ping","family":"Luo","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","year":"2023","journal-title":"Claude"},{"key":"ref3","article-title":"Screenai: A vision-language model for ui and infographics understanding","author":"Baechler","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/235"},{"key":"ref5","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s00779-010-0342-4"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref8","article-title":"Mobile app tasks with iterative feedback (motif): Addressing task feasibility in interactive visual environments","author":"Burns","year":"2021","journal-title":"arXiv preprint"},{"key":"ref9","article-title":"Amex: Android multi-annotation expo dataset for mobile gui agents","author":"Chai","year":"2024","journal-title":"arXiv preprint"},{"key":"ref10","article-title":"Gui-world: A dataset for gui-oriented multimodal 11 m -based agents","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Guicourse: From general vision language models to versatile gui agents","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref12","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.505"},{"key":"ref15","article-title":"Appagent: Multimodal agents as smartphone users","author":"Chi","year":"2023","journal-title":"arXiv preprint"},{"issue":"240","key":"ref16","first-page":"1","article-title":"Palm: Scaling language modeling with pathways","volume":"24","author":"Chowdhery","year":"2023","journal-title":"Journal of Machine Learning Research"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1220"},{"key":"ref18","article-title":"The llama 3 herd of models","author":"Dubey","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Multimodal web navigation with instruction-finetuned foundation models","author":"Furuta","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Navigating the digital world as humans do: Universal visual grounding for gui agents","author":"Gou","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"A realworld webagent with planning, long context understanding, and program synthesis","author":"Gur","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.371"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01354"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_10"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.50"},{"key":"ref26","article-title":"On the effects of data scale on computer control agents","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.729"},{"key":"ref28","article-title":"Appagent v2: Advanced agent for flexible mobile interactions","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Ferret-ui 2: Mastering universal user interface understanding across platforms","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref31","article-title":"Visualwebbench: How far have multimodal 11 ms evolved in web page understanding and grounding?","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"Weblinx: Real-world website navigation with multi-turn dialogue","author":"Han L\u00f9","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"Omniparser for pure vision based gui agent","author":"Lu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"Embodiedgpt: Vision-language pre-training via embodied chain of thought","volume":"36","author":"Mu","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1146\/annurev-control-062823-024352"},{"key":"ref36","year":"2024","journal-title":"Gpt4o"},{"key":"ref37","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref38","article-title":"Android in the wild: A largescale dataset for android device control","author":"Rawles","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","article-title":"Androidworld: A dynamic benchmarking environment for autonomous agents","author":"Rawles","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Code llama: Open foundation models for code","author":"Roziere","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2997"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1490"},{"key":"ref43","article-title":"Hugginggpt: Solving ai tasks with chatgpt and its friends in hugging face","volume":"36","author":"Shen","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref44","first-page":"31353144","article-title":"World of bits: An open-domain platform for web-based agents","volume-title":"Proceedings of the 34th International Conference on Machine Learning","author":"Shi"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.449"},{"key":"ref46","article-title":"Llama: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref47","article-title":"Ugif: Ui grounded instruction following","author":"Gubbi Venkatesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref48","article-title":"Mobile-agent-v2: Mobile device operation assistant with effective navigation via multi-agent collaboration","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref49","article-title":"Mobile-agent: Autonomous multi-modal mobile device agent with visual perception","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1186\/s13040-024-00371-3"},{"key":"ref52","article-title":"Os-copilot: Towards generalist computer agents with self-improvement","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","article-title":"Os-atlas: A foundation action model for generalist gui agents","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Osworld: Benchmarking multimodal agents for open-ended tasks in real computer environments","author":"Xie","year":"2024","journal-title":"arXiv preprint"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671650"},{"key":"ref56","article-title":"Wizardlm: Empowering large language models to follow complex instructions","author":"Xu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref57","article-title":"Gpt-4v in wonderland: Large multimodal models for zero-shot smartphone gui navigation","author":"Yan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref58","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in gpt-4v","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Mm-react: Prompting chatgpt for multimodal reasoning and action","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1508"},{"key":"ref61","article-title":"React: Synergizing reasoning and acting in language models","author":"Yao","year":"2022","journal-title":"arXiv preprint"},{"key":"ref62","article-title":"Mmt-bench: A comprehensive multimodal benchmark for evaluating large vision-language models towards multitask agi","author":"Ying","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","first-page":"240","article-title":"Ferret-ui: Grounded mobile ui understanding with multimodal 11 ms","volume-title":"European Conference on Computer Vision","author":"You"},{"key":"ref64","article-title":"You only look at screens: Multimodal chain-of-action agents","author":"Zhan","year":"2023","journal-title":"arXiv preprint"},{"key":"ref65","article-title":"Ufo: A ui-focused agent for windows os interaction","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.702"},{"key":"ref67","article-title":"Gpt-4v(ision) is a generalist web agent, if grounded","volume-title":"Forty-first International Conference on Machine Learning","author":"Zheng"},{"key":"ref68","article-title":"Webarena: A realistic web environment for building autonomous agents","author":"Zhou","year":"2023","journal-title":"arXiv preprint"},{"key":"ref69","article-title":"Ghost in the minecraft: Generally capable agents for open-world enviroments via large language models with text-based knowledge and memory","author":"Zhu","year":"2023","journal-title":"arXiv preprint"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444925.pdf?arnumber=11444925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:07:53Z","timestamp":1777612073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444925\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02080","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}